{
  "markdown": "# Awesome Agent Skills\n\n[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n[![Skills](https://img.shields.io/badge/skills-26-green.svg)](skills)\n\n**English** | [中文](README.zh-CN.md)\n\n**Repository**: https://github.com/YangsonHung/awesome-agent-skills\n\nA collection of AI Agent Skills that provide professional domain capabilities for intelligent assistants like Claude Code.\n\n## Features\n\n- **Modular Design** - Load skills on demand\n- **Bilingual Support** - Every skill is maintained as an English and Chinese pair\n- **Language Guardrails** - English `SKILL.md` files stay English-only, except native language names in `multi-lang-readme`\n- **Rich Resources** - Complete references and templates for each skill\n\n## Available Skills\n\n| Skill | Language | Description | Capabilities |\n|-------|----------|-------------|--------------|\n| [novel-writer](skills/en/novel-writer/SKILL.md) | English | Professional novel writing assistant for the entire creative process | Create novels, Continue chapters, Character design, Worldbuilding |\n| [multi-lang-readme](skills/en/multi-lang-readme/SKILL.md) | English | Create multilingual README translations | Translate README to English, German, Japanese, Korean, Chinese |\n| [conversation-json-to-md](skills/en/conversation-json-to-md/SKILL.md) | English | Convert chat-export JSON into one-conversation-per-file Markdown | Auto-detect formats, Q/A extraction, heading normalization, second-pass formatting |\n| [topic-bookmarks-reorganizer](skills/en/topic-bookmarks-reorganizer/SKILL.md) | English | Reorganize one topic folder from bookmarks export into clean importable HTML | Topic extraction, link regrouping, URL dedupe, browser-importable output |\n| [wechat-theme-extractor](skills/en/wechat-theme-extractor/SKILL.md) | English | Extract theme styles from WeChat articles and update converter config | WeChat HTML extraction, style analysis, theme generation, config injection |\n| [weixin-article-to-obsidian](skills/en/weixin-article-to-obsidian/SKILL.md) | English | Save Weixin articles into Obsidian with local images | opencli download, HTML fallback parsing, image localization, Obsidian asset links |\n| [mac-software-storage-cleanup](skills/en/mac-software-storage-cleanup/SKILL.md) | English | Audit macOS software storage usage and run prioritized cleanup | Installed software inventory, storage audit, safe cleanup, reclaim recommendations |\n| [ui-layout-analyzer](skills/en/ui-layout-analyzer/SKILL.md) | English | Analyze UI screenshots and describe layout plus functional structure | UI structure recognition, interaction analysis, element inventory, layout explanation |\n| [yuque-lakebook-export](skills/en/yuque-lakebook-export/SKILL.md) | English | Export Yuque `.lakebook` files into Markdown folders for Obsidian | Yuque export, lakebook conversion, Obsidian migration, image/assets handling, cropped image support |\n| [tweetclaw-twitter-automation](skills/en/tweetclaw-twitter-automation/SKILL.md) | English | Use TweetClaw safely for approved X/Twitter automation from agents | Tweet scraping, reply search, follower export, user lookup, media, DMs, monitors, webhooks, giveaway draws, approved posts/replies |\n| [git-weekly-report](skills/en/git-weekly-report/SKILL.md) | English | Summarize git commit logs into structured weekly reports | Multi-repo extraction, date range filtering, commit categorization, weekly report generation |\n| [git-push-secondary-merge-primary](skills/en/git-push-secondary-merge-primary/SKILL.md) | English | Commit & push secondary branch, then merge into the primary branch | Two-branch sync, branch detection, conventional commit, merge commit preservation, safe push |\n| [git-pushing-fast](skills/en/git-pushing-fast/SKILL.md) | English | Fast single-branch commit and push workflow with segmented commit body | Status inspection, staging, Conventional Commits, segmented body, safe push |\n| [git-commit-only](skills/en/git-commit-only/SKILL.md) | English | Create one local Conventional Commit without pushing | Status inspection, staging, Conventional Commits, segmented body, no push |\n| [frontend-quality-guardrails](skills/en/frontend-quality-guardrails/SKILL.md) | English | Build and review frontend UI with text, layout, visual, and browser QA guardrails | Long text handling, overflow fixes, visual standards, code review, responsive verification |\n| [react-component-hook-guidelines](skills/en/react-component-hook-guidelines/SKILL.md) | English | Review and split React components and custom Hooks by responsibility boundaries | Responsibility boundaries, props design, state flow, branch control, page orchestration |\n| [logo-design-board](skills/en/logo-design-board/SKILL.md) | English | Design and critique logo concepts with a distilled designer board | Brand intake, designer lenses, concept territories, visual prompts, logo quality scoring |\n| [linkedin](skills/en/linkedin/SKILL.md) | English | Automate LinkedIn from the command line via the linkedin CLI | Profile/company fetch and search, messaging, connection requests, posting, reactions and comments, data extraction |\n| [feature-doc-splitter](skills/en/feature-doc-splitter/SKILL.md) | English | Split rough feature notes into overview, frontend, and backend implementation docs | Codebase inspection, frontend/backend separation, Mermaid flows, API contracts, optional design placeholders |\n| [routerbase-api-integration](skills/en/routerbase-api-integration/SKILL.md) | English | Integrate applications with [routerbase](https://routerbase.com/) as an OpenAI-compatible gateway | SDK migration, base URL setup, streaming, tool calling, safe API keys |\n| [routerbase-model-routing](skills/en/routerbase-model-routing/SKILL.md) | English | Plan [routerbase](https://routerbase.com/) model routing, fallback, cost, and latency policies | Model selection, fallback chains, rollout checks, routing assumptions |\n| [routerbase-media-generation](skills/en/routerbase-media-generation/SKILL.md) | English | Build [routerbase](https://routerbase.com/) image, audio, and video generation workflows | Endpoint selection, retries, polling, asset handling, safety checks |\n| [x-twitter-scraper](skills/en/x-twitter-scraper/SKILL.md) | English | Plan X/Twitter data workflows with Xquik | Tweet search, profile timelines, follower export, media download, monitors, webhooks, MCP |\n| [ax-extract-workflow](skills/en/ax-extract-workflow/SKILL.md) | English | Reconstruct shipped work from local ax session evidence | Session lookup, tool and skill tracing, decision recovery, repeatable workflow brief |\n| [tree-ring-memory](skills/en/tree-ring-memory/SKILL.md) | English | Use Tree Ring Memory for local-first AI agent memory lifecycle work | Recall, evidence-linked lessons, privacy-safe capture, audit, redaction, forgetting |\n| [xquik-data](skills/en/xquik-data/SKILL.md) | English | Plan Xquik REST, OpenAPI, MCP, webhook, and SDK workflows for X/Twitter data | X data collection, API planning, MCP setup, webhook handoff, traceable reports |\n\n### Trigger Examples\n\n**linkedin:**\n- \"send a LinkedIn connection request to this profile\"\n- \"message this person on LinkedIn\"\n- \"search LinkedIn for marketing managers and extract their profiles\"\n- \"post this update to my LinkedIn\"\n**novel-writer:**\n- \"help me write a sci-fi novel\"\n- \"write the next chapter\"\n- \"design a villain character\"\n- \"build a cyberpunk world\"\n\n**multi-lang-readme:**\n- \"create bilingual README\"\n- \"translate README to Japanese\"\n- \"add German README version\"\n\n**conversation-json-to-md:**\n- \"convert this chat-export json to markdown files\"\n- \"one conversation per md file\"\n- \"keep only user and assistant Q/A\"\n- \"normalize output headings after export\"\n\n**topic-bookmarks-reorganizer:**\n- \"reorganize this bookmarks export and keep only the AI folder\"\n- \"analyze links under one topic folder and regroup them\"\n- \"dedupe repeated bookmark URLs and export importable html\"\n\n**wechat-theme-extractor:**\n- \"extract a theme from this WeChat article URL\"\n- \"generate a markdown-wechat-converter theme from this article\"\n- \"write the extracted style into markdown-to-wechat.html\"\n\n**weixin-article-to-obsidian:**\n- \"save this Weixin article into my Obsidian vault with local images\"\n- \"download this mp.weixin.qq.com article as Markdown\"\n- \"convert this WeChat article to an Obsidian note and localize images\"\n\n**mac-software-storage-cleanup:**\n- \"audit installed software sizes on my Mac\"\n- \"show safe cache and simulator cleanup candidates\"\n- \"give me a macOS storage cleanup plan\"\n\n**ui-layout-analyzer:**\n- \"analyze this UI screenshot\"\n- \"describe this interface layout\"\n- \"what does this UI do\"\n- \"output the layout and function description of this UI\"\n\n**yuque-lakebook-export:**\n- \"export this Yuque .lakebook to markdown\"\n- \"convert my lakebook into an Obsidian folder\"\n- \"batch convert multiple .lakebook files\"\n- \"fix missing images and broken internal links from Yuque export\"\n\n**tweetclaw-twitter-automation:**\n- \"scrape tweets with TweetClaw\"\n- \"search tweet replies for this post\"\n- \"post this approved tweet through OpenClaw\"\n- \"export followers and summarize the result\"\n\n**git-weekly-report:**\n- \"generate a weekly report from my git commits\"\n- \"summarize what I did this week across my projects\"\n- \"create a weekly report from recent git activity\"\n- \"review commits by project from last week\"\n\n**git-push-secondary-merge-primary:**\n- \"commit and push dev, then merge it into main and push\"\n- \"push the work branch then merge to master\"\n- \"merge develop into main, push both branches, and switch back to develop\"\n- \"finish the work branch and sync it to the primary branch\"\n\n**git-pushing-fast:**\n- \"commit and push these changes\"\n- \"push this work to the current branch\"\n- \"save this work to remote\"\n- \"commit with a segmented body and push\"\n\n**git-commit-only:**\n- \"commit these changes without pushing\"\n- \"create a local commit\"\n- \"commit current changes only\"\n- \"save this work locally as a commit\"\n\n**frontend-quality-guardrails:**\n- \"review this React component for long text and layout overflow\"\n- \"fix the mobile overflow and alignment issues in this dashboard\"\n- \"polish this form and verify responsive UI states\"\n- \"check this table for truncation, wrapping, and browser layout pitfalls\"\n\n**react-component-hook-guidelines:**\n- \"review this React component for split boundaries\"\n- \"split this god component into Hooks and presentation components\"\n- \"refactor this page to reduce props and state coupling\"\n- \"check whether this Hook should move logic into utils\"\n\n**logo-design-board:**\n- \"design a logo for this AI note-taking app\"\n- \"use a designer board to create brand mark directions\"\n- \"critique these logo concepts and choose the strongest one\"\n- \"turn this brand brief into logo prompts and vector notes\"\n\n**feature-doc-splitter:**\n- \"split this rough feature doc into overview, frontend, and backend docs\"\n- \"turn this initial product note into implementation documents\"\n- \"read the codebase and write frontend/backend build docs\"\n- \"add Mermaid flows and ask whether to reserve design placeholders\"\n\n**routerbase-api-integration:**\n- \"migrate this OpenAI SDK call to RouterBase\"\n- \"set up RouterBase as an OpenAI-compatible endpoint\"\n- \"write a safe RouterBase API integration example\"\n\n**routerbase-model-routing:**\n- \"choose RouterBase models for this workload\"\n- \"design a fallback chain for RouterBase\"\n- \"write cost-aware model routing rules\"\n\n**routerbase-media-generation:**\n- \"build a RouterBase image generation workflow\"\n- \"handle RouterBase video generation polling\"\n- \"add safety checks for generated media assets\"\n\n**x-twitter-scraper:**\n- \"search X posts for this keyword\"\n- \"export followers for this account\"\n- \"set up an X monitor with a webhook\"\n- \"choose the right Xquik endpoint for this workflow\"\n**ax-extract-workflow:**\n- \"how did we ship this feature\"\n- \"extract workflow from this commit\"\n- \"what made this PR work\"\n- \"reconstruct the recipe behind yesterday's demo\"\n**tree-ring-memory:**\n- \"recall what we decided before changing this repo\"\n- \"remember this lesson with evidence\"\n- \"audit project memory before this release\"\n- \"redact or forget stale memory about this task\"\n**xquik-data:**\n- \"collect X posts with Xquik and summarize the results\"\n- \"design an Xquik API workflow for this monitor\"\n- \"use the Xquik MCP server for this social data task\"\n- \"turn these Xquik webhook events into a handoff report\"\n\n## Quick Start\n\n### Installation\n\nInstall with one of the following commands:\n\n```bash\nnpx skills add YangsonHung/awesome-agent-skills\n```\n\n```bash\nbunx skills add YangsonHung/awesome-agent-skills\n```\n\n```bash\npnpm dlx skills add YangsonHung/awesome-agent-skills\n```\n\nList available skills in this repository:\n\n```bash\nnpx skills add YangsonHung/awesome-agent-skills --list\n```\n\n```bash\nbunx skills add YangsonHung/awesome-agent-skills --list\n```\n\n```bash\npnpm dlx skills add YangsonHung/awesome-agent-skills --list\n```\n\nInstall a specific skill:\n\n```bash\nnpx skills add YangsonHung/awesome-agent-skills --skill yuque-lakebook-export\n```\n\n```bash\nbunx skills add YangsonHung/awesome-agent-skills --skill yuque-lakebook-export\n```\n\n```bash\npnpm dlx skills add YangsonHung/awesome-agent-skills --skill yuque-lakebook-export\n```\n\nInstall a specific skill globally:\n\n```bash\nnpx skills add YangsonHung/awesome-agent-skills --skill yuque-lakebook-export -g\n```\n\nInstall a specific skill to a specific agent:\n\n```bash\nnpx skills add YangsonHung/awesome-agent-skills --skill yuque-lakebook-export -a claude-code\n```\n\nInstall a specific skill without confirmation prompts:\n\n```bash\nnpx skills add YangsonHung/awesome-agent-skills --skill yuque-lakebook-export -y\n```\n\nInstall a specific skill globally for a specific agent without prompts:\n\n```bash\nnpx skills add YangsonHung/awesome-agent-skills --skill yuque-lakebook-export -g -a claude-code -y\n```\n\nOr install manually by copying the English skills only:\n\n```bash\ncp -r skills/en/* ~/.claude/skills/\n```\n\nMore command usage examples:\n\nhttps://github.com/vercel-labs/skills/blob/main/README.md\n\n### Usage\n\nOnce installed, the skills will be automatically available in Claude Code. Simply ask Claude to perform a task related to a skill, and it will use the appropriate skill automatically.\n\n## Contributing\n\nContributions are welcome! To add a new skill:\n\n1. Fork this repository\n2. Create both paired directories under `skills/en/` and `skills/zh-cn/`\n3. Include the following files:\n   - `SKILL.md` - Main skill definition with frontmatter\n   - `README.md` - Optional skill-level notes\n   - `scripts/` - Optional helper scripts\n   - `references/` - Optional reference materials\n   - `assets/` - Optional templates and resources\n4. Ensure both language variants are added together and kept in sync\n5. Keep English `SKILL.md` files free of Chinese/Han characters; add Chinese examples and localized wording only to the paired `skills/zh-cn/` skill. The exception is `skills/en/multi-lang-readme/SKILL.md`, where language-switch examples may show native language names.\n6. Keep frontmatter `description` concise because it is used as routing metadata for skill selection:\n   - English descriptions must start with `Use when ...`\n   - Chinese descriptions must use natural Chinese trigger wording, not the English phrase `Use when`\n   - Do not mention a specific agent in descriptions; describe the user need or task\n   - Put longer purpose, capabilities, outputs, and boundaries in `## Overview`\n7. Submit a pull request\n\n### Test SKILL.md\n\nBefore opening a PR, validate skill files locally. The validators check skill structure, bilingual counterparts, and the English `SKILL.md` language rule:\n\n```bash\npython3 scripts/validate_skills.py\nnode scripts/validate-skills.js\n```\n\nFor CI-level checks (fail on warnings), run strict mode:\n\n```bash\npython3 scripts/validate_skills.py --strict\nnode scripts/validate-skills.js --strict\n```\n\nBoth commands must exit with code `0`.\n\n### Git Hooks\n\nEnable the repository pre-commit hook locally:\n\n```bash\ngit config core.hooksPath .githooks\n```\n\nThe hook runs strict skill validators, including the English skill language check, before each commit.\n\n### Skill Format\n\n```markdown\n---\nname: skill-name\ndescription: Use when performing a concise task-specific trigger condition.\n---\n\n# Skill Name\n\n## Overview\n\nExplain the skill's purpose, capabilities, outputs, and boundaries.\n\n## When to Use\n\nUse this skill when the user asks for:\n- Concrete trigger example\n- Another supported task\n```\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n",
  "bytes": 16610,
  "sha": "093dc5f266d5b9766917c6da86da7884847dc1e352ca1477fd7d283c4e9e02b5",
  "repo_slug": "yangsonhung/awesome-agent-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_yangsonhung_awesome_agent_skills_novel_w_54e2be53/readme"
}